mac-screen-search: CLI find, highlight, redact text on screen, in files
Screen OCR search with redaction in a single Swift CLI—no dependencies beyond macOS.
Screenshots are summarized and OCR'd by configurable model endpoints (managed OpenRouter key or BYO/local Ollama) and only short text snippets are kept in a local SQLite DB — neat engineering to convert raw screen noise into searchable memory. The managed-key option lowers onboarding friction, but shipping images off-device by default is a real privacy tradeoff users should weigh. Practical, clever, and clearly built with real usage (timesheets, resume-of-work queries) in mind.
Knowledge workers, developers, freelancers and teams who need automated time tracking, searchable activity history, or richer context for AI assistants
Most people we showed it to started using it to generate timesheets.
Any ideas for what else this could do are welcome!
Website: https://trymemorylane.com/
Screen OCR search with redaction in a single Swift CLI—no dependencies beyond macOS.
CPU-only VLM OCR beats Tesseract on layout without needing CUDA or cloud APIs.
Open-source Rewind alternative with diff-based OCR and a local HTTP API for agents.
CPU-only VLM OCR beats Tesseract accuracy without sending data to the cloud.
Screen snips execute commands instead of chat—closes the AI-to-action gap beautifully.
Native iOS screenshot stitching with smart overlap detection, but solves a narrow niche.